tensorflow学习——tf.layers.batch_normalization/tf.nn.batch_normalization/tf.contrib.layers.batch_norm

图片归一化方法：

import tensorflow as tfa=tf.constant([1.,2.,3.,4.,7.,5.,8.,4.,6.],shape=(1,3,3,3)) a_mean, a_var = tf.nn.moments(a, axes=[1,2],keep_dims=True)b=tf.rsqrt(a_var)c=(a-a_mean)*b  # c 和 d 算的结果相同，是对整个batch图片归一化# 只有当batch_size为 1 时，结果才与e,f值相同d=tf.nn.batch_normalization(a,a_mean,a_var,offset=None,scale=1,variance_epsilon=0)% e和 f 算的结果相同，是对batch中的每张图片归一化e=tf.layers.batch_normalization(a,training=True)f=tf.contrib.layers.batch_norm(a,is_training=True)sess = tf.Session()sess.run(tf.global_variables_initializer())mean,var=sess.run([a_mean,a_var])a_value,b_value,c_value,d_value,e_value,f_value=sess.run([a,b,c,d,e,f])sess.close()

import tensorflow as tfimport numpy as npa=np.array([[5.,8.,2.],[7.,9.,1.]])a=np.expand_dims(a,axis=0)a=tf.constant(a,dtype=tf.float32) a_mean, a_var = tf.nn.moments(a, axes=[0,1],keep_dims=True)b=tf.rsqrt(a_var)c=(a-a_mean)*bd=tf.layers.batch_normalization(a,training=True)e=tf.nn.batch_normalization(a,a_mean,a_var,offset=None,scale=1,variance_epsilon=0)sess = tf.Session()sess.run(tf.global_variables_initializer())a_value,b_value,c_value,d_value,e_value=sess.run([a,b,c,d,e])sess.close()